Building robust agent systems requires much more than simply stringing together prompts in a linear fashion. While many projects start with simple chains, productive deployment requires architectures that can reliably handle errors, process asynchronous events, and manage complex states.
In this presentation, we take a concise look at modern orchestration approaches for AI agents, analyze their strengths and weaknesses, and show which type of architecture is suitable for which challenges – from simple pipelines to graph structures to decoupled multi-agent systems. Participants will gain an overview of how to select the right orchestration pattern for their specific requirements and build systems that grow with increasing complexity.

Speakers:

Martin Brandl (CTO, white duck)

André Ratzenberger (Senior Software & AI Architect, white duck)

👉🏼 Purchase your ticket by following this link.